Submission to metric track

Introduction

Choosing between man- and zone coverage is one of the most important strategic decisions of a defensive coordinator prior to each play in American football. While experienced coaches and quarterbacks can often identify these defensive strategies visually, the growing availability of tracking data presents another opportunity to infer the underlying tactic. This project aims to leverage hidden Markov models (HMMs) to detect defensive strategies — man or zone coverage — based on pre-snap player movement data. By modeling hidden states that represent the offensive player to be guarded, this approach provides a data-driven framework for unraveling the complexity of defensive patterns and enables real-time tactical insights for coaching and analysis.

Data

This video displays a touchdown from the Kansas City Chiefs against the Arizona Cardinals in Week 1 of the 2022 NFL season. We can see that, pre-snap, Mecole Hardman (KC #17) travels from the left side to the right side, followed by the defender Marco Wilson (AZ #20), i.e. a clear indication for man-coverage.

Analysis

Our analysis comprises different steps:

1. Pre-Motion Analysis

We train a model to predict whether the defense plays a man- or zone coverage scheme. The model uses the previously described features, blablabla

2. HMM Analysis

We model the movements of defensive players during the phase of pre-snap motion within a hidden Markov framework, in which the underlying states represent the offensive players to be guarded (see Franks et al., 2015 for a similar approach in basketball). In contrast to Groom et al., 2024, who enforce a state to proxy zone coverage during corner kicks in soccer, we cannot do that as the classical zones in American football will only be covered post-snap. To remidiate this problem, we aim to derive the decision of man- or zone coverage from the number of switches for individual players. In particular, a low number of switches when offensive players are in motion indicates man coverage whereas a higher number indicates zone coverage.

3. Post-Motion Analysis

We re-train the pre-motion model to predict whether the defense plays a man- or zone coverage scheme, however, in this step, we incorporate the results from the HMM analysis.

4. Motion evaluation

By comparing the predictive performance of our pre-motion model and our post-motion model we can determine the effectiveness of motion to detect the correct defensive scheme.

Code

All code for data preprocessing, model training, prediction and player evaluation can be found here.

References

*Franks A, Miller A, Bornn L, Goldsberry K (2015). Characterizing the Spatial Structure of Defensive Skill in Professional Basketball. The Annals of Applied Statistics, 9(1), DOI:10.1214/14-AOAS799

*Zucchini W, MacDonald I, Langrock R (2016). Hidden Markov Models for Time Series - An Introduction Using R. CRC Press